Research On Guidance Technology Of Micro-miniature Unmanned Aerial Vehicles

Miniature unmanned flight vehicle has the characteristics of small volume, light weight, low cost, strong flexibility, single carry, good concealment, convenient operation, etc. Therefore, these flight vehicles are widely used in military and civilian fields. Many countries pay great attention to the miniature unmanned flight vehicle and devoted a lot of manpower and material resources to develop.This thesis takes miniature unmanned flight vehicle as research object and designs the guidance laws to make its relative height lower and relative velocity higher. Through analyzing the aerodynamic configuration of the miniature unmanned flight vehicle, a new aerodynamic optimization design plan which can improve the maneuverability of miniature unmanned flight vehicle effectively is presented. The guidance law based on reinforcement learning is designed. The look angle guidance laws with multiple constraints for miniature unmanned flight vehicle are presented. The feasibility of the guidance laws are validated through the numerical simulation. The feasibility of the design scheme is validated through the hardware-in-the-loop simulation. The main contents are as follows:Through analyzing the aerodynamic configuration of the miniature unmanned flight vehicle, a new aerodynamic optimization design plan which can improve the maneuverability of miniature unmanned flight vehicle effectively is presented. With the three-dimensional modeling of aerodynamic shape for the miniature unmanned flight vehicle completed, the aerodynamic characteristics under the condition of subsonic are calculated using the computational fluid dynamics method. The results show that the miniature unmanned flight vehicle with good maneuverability is presented and the purpose of the aerodynamic optimization design is implemented.The reinforcement learning and neural networks are researched and applied to the guidance of the miniature unmanned flight vehicle. The flight of the miniature unmanned flight vehicle is controlled through calculating the state-action value functions. The policy and the action are optimized through the appraising function of the environment, then the guidance law based on reinforcement learning is designed and the feasibility of the guidance laws is validated through numerical simulation.In order to solve the problem that the line of sight angle is obtained through the complex calculations to use the proportional navigation guidance law of the small guided strapdown miniature unmanned flight vehicle, the look angle guidance law which don't need the line of sight angle is presented and the feasibility of the guidance laws is validated through numerical simulation.In order to solve the problem of impact angle constraint and field of view limit for the miniature flight vehicle guidance, a look angle guidance law with terminal constraint for miniature unmanned flight vehicle is presented and the feasibility of the guidance laws is validated through numerical simulation.